© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16012
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate frequency or repetition, particularly in relation to activities and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "It is" or "it's" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    certainty, difficulty, possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IconModule
    -0.56
    ItemLayout
    -0.55
    RRect
    -0.55
     Photocase
    -0.53
     einges
    -0.51
     використо
    -0.51
     frattempo
    -0.50
     Gorg
    -0.49
    HasIndex
    -0.49
     समीक्षाएं
    -0.49
    POSITIVE LOGITS
     quite
    0.73
     obvious
    0.67
     really
    0.66
     متعلقه
    0.63
     kinda
    0.63
     obvio
    0.62
     something
    0.59
    Obvious
    0.59
     very
    0.58
     Quite
    0.58
    Activations Density 0.228%

    No Known Activations